Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation. In this paper, our ConvMAE framework demonstrates that multi-scale hybrid convolution-transformer can learn more discriminative representations via the mask auto-encoding scheme. However, directly using the original masking strategy leads to the heavy computational cost and pretraining-finetuning discrepancy. To tackle the issue, we adopt the masked convolution to prevent information leakage in the convolution blocks. A simple block-wise masking strategy is proposed to ensure computational efficiency. We also propose to more directly supervise the multi-scale features of the encoder to boost multi-scale features. Based on our pretrained ConvMAE models, ConvMAE-Base improves ImageNet-1K finetuning accuracy by 1.4% compared with MAE-Base. On object detection, ConvMAE-Base finetuned for only 25 epochs surpasses MAE-Base fined-tuned for 100 epochs by 2.9% box AP and 2.2% mask AP respectively. Code and pretrained models are available at https://github.com/Alpha-VL/ConvMAE.
Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires training a fixed discrete Variational AutoEncoder (dVAE) before pre-training, which results in a complex two-stage method called Point-BERT. Inspired by BERT and MoCo, we propose POS-BERT, a one-stage BERT pre-training method for point clouds. Specifically, we use the mask patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patches information under the supervision of the corresponding tokenizer output. Unlike Point-BERT, its tokenizer is extra-trained and frozen. We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process. Further, in order to learn high-level semantic representation, we combine contrastive learning to maximize the class token consistency between different transformation point clouds. Extensive experiments have demonstrated that POS-BERT can extract high-quality pre-training features and promote downstream tasks to improve performance. Using the pre-training model without any fine-tuning to extract features and train linear SVM on ModelNet40, POS-BERT achieves the state-of-the-art classification accuracy, which exceeds Point-BERT by 3.5\%. In addition, our approach has significantly improved many downstream tasks, such as fine-tuned classification, few-shot classification, part segmentation. The code and trained-models will be available at: \url{https://github.com/fukexue/POS-BERT}.
Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are trained independently using different datasets since they expect to learn distinctive acoustic features. However, humans can distinguish language content and the speaker identity simultaneously. Motivated by this, we believe it is important to explore a method that can effectively extract common features while decoupling task-specific features. Bearing this in mind, a two-branch deep network (KWS branch and SV branch) with the same network structure is developed and a novel decoupling feature learning method is proposed to push up the performance of KWS and SV simultaneously where speaker-invariant keyword representations and keyword-invariant speaker representations are expected respectively. Experiments are conducted on Google Speech Commands Dataset (GSCD). The results demonstrate that the orthogonality regularization helps the network to achieve SOTA EER of 1.31% and 1.87% on KWS and SV, respectively.
Monocular 3D object detection has long been a challenging task in autonomous driving, which requires to decode 3D predictions solely from a single 2D image. Most existing methods follow conventional 2D object detectors to first localize objects by their centers, and then predict 3D attributes using center-neighboring local features. However, such center-based pipeline views 3D prediction as a subordinate task and lacks inter-object depth interactions with global spatial clues. In this paper, we introduce a simple framework for Monocular DEtection with depth-aware TRansformer, named MonoDETR. We enable the vanilla transformer to be depth-aware and enforce the whole detection process guided by depth. Specifically, we represent 3D object candidates as a set of queries and produce non-local depth embeddings of the input image by a lightweight depth predictor and an attention-based depth encoder. Then, we propose a depth-aware decoder to conduct both inter-query and query-scene depth feature communication. In this way, each object estimates its 3D attributes adaptively from the depth-informative regions on the image, not limited by center-around features. With minimal handcrafted designs, MonoDETR is an end-to-end framework without additional data, anchors or NMS and achieves competitive performance on KITTI benchmark among state-of-the-art center-based networks. Extensive ablation studies demonstrate the effectiveness of our approach and its potential to serve as a transformer baseline for future monocular research. Code is available at https://github.com/ZrrSkywalker/MonoDETR.git.
Anti-cancer drug discoveries have been serendipitous, we sought to present the Open Molecular Graph Learning Benchmark, named CandidateDrug4Cancer, a challenging and realistic benchmark dataset to facilitate scalable, robust, and reproducible graph machine learning research for anti-cancer drug discovery. CandidateDrug4Cancer dataset encompasses multiple most-mentioned 29 targets for cancer, covering 54869 cancer-related drug molecules which are ranged from pre-clinical, clinical and FDA-approved. Besides building the datasets, we also perform benchmark experiments with effective Drug Target Interaction (DTI) prediction baselines using descriptors and expressive graph neural networks. Experimental results suggest that CandidateDrug4Cancer presents significant challenges for learning molecular graphs and targets in practical application, indicating opportunities for future researches on developing candidate drugs for treating cancers.
In this paper, we propose a simple and general framework for self-supervised point cloud representation learning. Human beings understand the 3D world by extracting two levels of information and establishing the relationship between them. One is the global shape of an object, and the other is the local structures of it. However, few existing studies in point cloud representation learning explored how to learn both global shapes and local-to-global relationships without a specified network architecture. Inspired by how human beings understand the world, we utilize knowledge distillation to learn both global shape information and the relationship between global shape and local structures. At the same time, we combine contrastive learning with knowledge distillation to make the teacher network be better updated. Our method achieves the state-of-the-art performance on linear classification and multiple other downstream tasks. Especially, we develop a variant of ViT for 3D point cloud feature extraction, which also achieves comparable results with existing backbones when combined with our framework, and visualization of the attention maps show that our model does understand the point cloud by combining the global shape information and multiple local structural information, which is consistent with the inspiration of our representation learning method. Our code will be released soon.
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been mainly driven by 3D convolutional neural networks and vision transformers. Although 3D convolution can efficiently aggregate local context to suppress local redundancy from a small 3D neighborhood, it lacks the capability to capture global dependency because of the limited receptive field. Alternatively, vision transformers can effectively capture long-range dependency by self-attention mechanism, while having the limitation on reducing local redundancy with blind similarity comparison among all the tokens in each layer. Based on these observations, we propose a novel Unified transFormer (UniFormer) which seamlessly integrates merits of 3D convolution and spatiotemporal self-attention in a concise transformer format, and achieves a preferable balance between computation and accuracy. Different from traditional transformers, our relation aggregator can tackle both spatiotemporal redundancy and dependency, by learning local and global token affinity respectively in shallow and deep layers. We conduct extensive experiments on the popular video benchmarks, e.g., Kinetics-400, Kinetics-600, and Something-Something V1&V2. With only ImageNet-1K pretraining, our UniFormer achieves 82.9%/84.8% top-1 accuracy on Kinetics-400/Kinetics-600, while requiring 10x fewer GFLOPs than other state-of-the-art methods. For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60.9% and 71.2% top-1 accuracy respectively. Code is available at https://github.com/Sense-X/UniFormer.
It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our UniFormer blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification. With only ImageNet-1K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks, e.g., it obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Something-Something V1/V2 video classification tasks, 53.8 box AP and 46.4 mask AP on COCO object detection task, 50.8 mIoU on ADE20K semantic segmentation task, and 77.4 AP on COCO pose estimation task. Code is available at https://github.com/Sense-X/UniFormer.
Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. In this paper, we introduce a ternary vision transformer (TerViT) to ternarize the weights in ViTs, which are challenged by the large loss surface gap between real-valued and ternary parameters. To address the issue, we introduce a progressive training scheme by first training 8-bit transformers and then TerViT, and achieve a better optimization than conventional methods. Furthermore, we introduce channel-wise ternarization, by partitioning each matrix to different channels, each of which is with an unique distribution and ternarization interval. We apply our methods to popular DeiT and Swin backbones, and extensive results show that we can achieve competitive performance. For example, TerViT can quantize Swin-S to 13.1MB model size while achieving above 79% Top-1 accuracy on ImageNet dataset.