Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory performance, which is usually unavailable for medical images. Additionally, due to the gap between medical and natural images, the improvement generated by the ImageNet pretrained weights significantly degrades while transferring the weights to medical image processing tasks. In this paper, we propose Bootstrap Own Latent of Transformer (BOLT), a self-supervised learning approach specifically for medical image classification with the Transformer backbone. Our BOLT consists of two networks, namely online and target branches, for self-supervised representation learning. Concretely, the online network is trained to predict the target network representation of the same patch embedding tokens with a different perturbation. To maximally excavate the impact of Transformer from limited medical data, we propose an auxiliary difficulty ranking task. The Transformer is enforced to identify which branch (i.e., online/target) is processing the more difficult perturbed tokens. Overall, the Transformer endeavours itself to distill the transformation-invariant features from the perturbed tokens to simultaneously achieve difficulty measurement and maintain the consistency of self-supervised representations. The proposed BOLT is evaluated on three medical image processing tasks, i.e., skin lesion classification, knee fatigue fracture grading and diabetic retinopathy grading. The experimental results validate the superiority of our BOLT for medical image classification, compared to ImageNet pretrained weights and state-of-the-art self-supervised learning approaches.

Despite some successful applications of goal-driven navigation, existing deep reinforcement learning-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled from the perception module and directly introduced as a condition of decision-making, resulting in the goal-irrelevant features of the scene representation playing an adversary role during the learning process. In light of this, we present a novel Goal-guided Transformer-enabled reinforcement learning (GTRL) approach by considering the physical goal states as an input of the scene encoder for guiding the scene representation to couple with the goal information and realizing efficient autonomous navigation. More specifically, we propose a novel variant of the Vision Transformer as the backbone of the perception system, namely Goal-guided Transformer (GoT), and pre-train it with expert priors to boost the data efficiency. Subsequently, a reinforcement learning algorithm is instantiated for the decision-making system, taking the goal-oriented scene representation from the GoT as the input and generating decision commands. As a result, our approach motivates the scene representation to concentrate mainly on goal-relevant features, which substantially enhances the data efficiency of the DRL learning process, leading to superior navigation performance. Both simulation and real-world experimental results manifest the superiority of our approach in terms of data efficiency, performance, robustness, and sim-to-real generalization, compared with other state-of-art baselines. Demonstration videos are available at \colorb{https://youtu.be/93LGlGvaN0c.

We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance cues and render realistic images, we train a point-cloud encoder within a devised point-based neural renderer by comparing the rendered images with real images on massive RGB-D data. The learned point-cloud encoder can be easily integrated into various downstream tasks, including not only high-level tasks like 3D detection and segmentation, but low-level tasks like 3D reconstruction and image synthesis. Extensive experiments on various tasks demonstrate the superiority of our approach compared to existing pre-training methods.

Fine-grained capturing of 3D HOI boosts human activity understanding and facilitates downstream visual tasks, including action recognition, holistic scene reconstruction, and human motion synthesis. Despite its significance, existing works mostly assume that humans interact with rigid objects using only a few body parts, limiting their scope. In this paper, we address the challenging problem of f-AHOI, wherein the whole human bodies interact with articulated objects, whose parts are connected by movable joints. We present CHAIRS, a large-scale motion-captured f-AHOI dataset, consisting of 16.2 hours of versatile interactions between 46 participants and 81 articulated and rigid sittable objects. CHAIRS provides 3D meshes of both humans and articulated objects during the entire interactive process, as well as realistic and physically plausible full-body interactions. We show the value of CHAIRS with object pose estimation. By learning the geometrical relationships in HOI, we devise the very first model that leverage human pose estimation to tackle the estimation of articulated object poses and shapes during whole-body interactions. Given an image and an estimated human pose, our model first reconstructs the pose and shape of the object, then optimizes the reconstruction according to a learned interaction prior. Under both evaluation settings (e.g., with or without the knowledge of objects' geometries/structures), our model significantly outperforms baselines. We hope CHAIRS will promote the community towards finer-grained interaction understanding. We will make the data/code publicly available.

Compared to typical multi-sensor systems, monocular 3D object detection has attracted much attention due to its simple configuration. However, there is still a significant gap between LiDAR-based and monocular-based methods. In this paper, we find that the ill-posed nature of monocular imagery can lead to depth ambiguity. Specifically, objects with different depths can appear with the same bounding boxes and similar visual features in the 2D image. Unfortunately, the network cannot accurately distinguish different depths from such non-discriminative visual features, resulting in unstable depth training. To facilitate depth learning, we propose a simple yet effective plug-and-play module, One Bounding Box Multiple Objects (OBMO). Concretely, we add a set of suitable pseudo labels by shifting the 3D bounding box along the viewing frustum. To constrain the pseudo-3D labels to be reasonable, we carefully design two label scoring strategies to represent their quality. In contrast to the original hard depth labels, such soft pseudo labels with quality scores allow the network to learn a reasonable depth range, boosting training stability and thus improving final performance. Extensive experiments on KITTI and Waymo benchmarks show that our method significantly improves state-of-the-art monocular 3D detectors by a significant margin (The improvements under the moderate setting on KITTI validation set are $\mathbf{1.82\sim 10.91\%}$ mAP in BEV and $\mathbf{1.18\sim 9.36\%}$ mAP in 3D}. Codes have been released at https://github.com/mrsempress/OBMO.

The quality of knowledge retrieval is crucial in knowledge-intensive conversations. Two common strategies to improve the retrieval quality are finetuning the retriever or generating a self-contained query, while they encounter heavy burdens on expensive computation and elaborate annotations. In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv. There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator. Without extra supervision, the end-to-end joint training of QKConv explores multiple candidate queries and utilizes corresponding selected knowledge to yield the target response. To evaluate the effectiveness of the proposed method, we conducted comprehensive experiments on conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation. Experimental results demonstrate that QKConv achieves state-of-the-art performance compared to unsupervised methods and competitive performance compared to supervised methods.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Although considerable progress has been obtained in neural network quantization for efficient inference, existing methods are not scalable to heterogeneous devices as one dedicated model needs to be trained, transmitted, and stored for one specific hardware setting, incurring considerable costs in model training and maintenance. In this paper, we study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. With this representation, we can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model. To this end, we propose a simple once quantization-aware training (QAT) scheme for obtaining high-performance vertical-layered models. Our design incorporates a cascade downsampling mechanism which allows us to obtain multiple quantized networks from one full precision source model by progressively mapping the higher precision weights to their adjacent lower precision counterparts. Then, with networks of different bit-widths from one source model, multi-objective optimization is employed to train the shared source model weights such that they can be updated simultaneously, considering the performance of all networks. By doing this, the shared weights will be optimized to balance the performance of different quantized models, thus making the weights transferable among different bit widths. Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width. Code will be available.

The pretraining-finetuning paradigm has demonstrated great success in NLP and 2D image fields because of the high-quality representation ability and transferability of their pretrained models. However, pretraining such a strong model is difficult in the 3D point cloud field since the training data is limited and point cloud collection is expensive. This paper introduces \textbf{E}fficient \textbf{P}oint \textbf{C}loud \textbf{L}earning (EPCL), an effective and efficient point cloud learner for directly training high-quality point cloud models with a frozen CLIP model. Our EPCL connects the 2D and 3D modalities by semantically aligning the 2D features and point cloud features without paired 2D-3D data. Specifically, the input point cloud is divided into a sequence of tokens and directly fed into the frozen CLIP model to learn point cloud representation. Furthermore, we design a task token to narrow the gap between 2D images and 3D point clouds. Comprehensive experiments on 3D detection, semantic segmentation, classification and few-shot learning demonstrate that the 2D CLIP model can be an efficient point cloud backbone and our method achieves state-of-the-art accuracy on both real-world and synthetic downstream tasks. Code will be available.

The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for dynamic and complex video-level understanding tasks. To fill the gap, we present general video foundation models, InternVideo, by taking advantage of both generative and discriminative self-supervised video learning. Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications. Without bells and whistles, InternVideo achieves state-of-the-art performance on 39 video datasets from extensive tasks including video action recognition/detection, video-language alignment, and open-world video applications. Especially, our methods can obtain 91.1% and 77.2% top-1 accuracy on the challenging Kinetics-400 and Something-Something V2 benchmarks, respectively. All of these results effectively show the generality of our InternVideo for video understanding. The code will be released at https://github.com/OpenGVLab/InternVideo .