In this paper, we consider the problem of disease diagnosis. Unlike the conventional learning paradigm that treats labels independently, we propose a knowledge-enhanced framework, that enables training visual representation with the guidance of medical domain knowledge. In particular, we make the following contributions: First, to explicitly incorporate experts' knowledge, we propose to learn a neural representation for the medical knowledge graph via contrastive learning, implicitly establishing relations between different medical concepts. Second, while training the visual encoder, we keep the parameters of the knowledge encoder frozen and propose to learn a set of prompt vectors for efficient adaptation. Third, we adopt a Transformer-based disease-query module for cross-model fusion, which naturally enables explainable diagnosis results via cross attention. To validate the effectiveness of our proposed framework, we conduct thorough experiments on three x-ray imaging datasets across different anatomy structures, showing our model is able to exploit the implicit relations between diseases/findings, thus is beneficial to the commonly encountered problem in the medical domain, namely, long-tailed and zero-shot recognition, which conventional methods either struggle or completely fail to realize.
In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario. To achieve this goal, we make the following contributions: (i) we start with a naive two-stage approach for open-vocabulary object detection and attribute classification, termed CLIP-Attr. The candidate objects are first proposed with an offline RPN and later classified for semantic category and attributes; (ii) we combine all available datasets and train with a federated strategy to finetune the CLIP model, aligning the visual representation with attributes, additionally, we investigate the efficacy of leveraging freely available online image-caption pairs under weakly supervised learning; (iii) in pursuit of efficiency, we train a Faster-RCNN type model end-to-end with knowledge distillation, that performs class-agnostic object proposals and classification on semantic categories and attributes with classifiers generated from a text encoder; Finally, (iv) we conduct extensive experiments on VAW, MS-COCO, LSA, and OVAD datasets, and show that recognition of semantic category and attributes is complementary for visual scene understanding, i.e., jointly training object detection and attributes prediction largely outperform existing approaches that treat the two tasks independently, demonstrating strong generalization ability to novel attributes and categories.
In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor, which only exploits web-crawled image-text pairs for pre-training without using any mask annotations. OVSegmentor assembles the image pixels into a set of learnable group tokens via a slot-attention based binding module, and aligns the group tokens to the corresponding caption embedding. Second, we propose two proxy tasks for training, namely masked entity completion and cross-image mask consistency. The former aims to infer all masked entities in the caption given the group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities. The latter enforces consistent mask predictions between images that contain shared entities, which encourages the model to learn visual invariance. Third, we construct CC4M dataset for pre-training by filtering CC12M with frequently appeared entities, which significantly improves training efficiency. Fourth, we perform zero-shot transfer on three benchmark datasets, PASCAL VOC 2012, PASCAL Context, and COCO Object. Our model achieves superior segmentation results over the state-of-the-art method by using only 3\% data (4M vs 134M) for pre-training. Code and pre-trained models will be released for future research.
The goal of this paper is to augment a pre-trained text-to-image diffusion model with the ability of open-vocabulary objects grounding, i.e., simultaneously generating images and segmentation masks for the corresponding visual entities described in the text prompt. We make the following contributions: (i) we insert a grounding module into the existing diffusion model, that can be trained to align the visual and textual embedding space of the diffusion model with only a small number of object categories; (ii) we propose an automatic pipeline for constructing a dataset, that consists of {image, segmentation mask, text prompt} triplets, to train the proposed grounding module; (iii) we evaluate the performance of open-vocabulary grounding on images generated from the text-to-image diffusion model and show that the module can well segment the objects of categories beyond seen ones at training time; (iv) we adopt the guided diffusion model to build a synthetic semantic segmentation dataset, and show that training a standard segmentation model on such dataset demonstrates competitive performance on zero-shot segmentation(ZS3) benchmark, which opens up new opportunities for adopting the powerful diffusion model for discriminative tasks.
In this paper, we consider the problem of enhancing self-supervised visual-language pre-training (VLP) with medical-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice. In particular, we make the following contributions: First, unlike existing works that directly process the raw reports, we adopt a novel report filter to extract the medical entities, avoiding unnecessary complexity from language grammar and enhancing the supervision signals; Second, we propose a novel entity embedding module by querying an external knowledge description base, to exploit the rich context of additional information that the medical domain affords, and implicitly build relationships between entities in the language embedding space; Third, we propose a novel Transformer-based fusion model for spatially aligning the entity description with visual signals at the image patch level only with self-supervised learning, thus enabling the ability for spatial grounding; Fourth, we conduct thorough experiments to validate the effectiveness of our proposed architecture, and benchmark on numerous public benchmarks e.g., ChestX-ray14, RSNA Pneumonia, SIIM-ACR Pneumothorax, COVIDx CXR-2, COVID Rural, and EdemaSeverity. In both zero-shot and fine-tuning settings, our model has demonstrated strong performance compared with the former methods on disease classification and grounding.
When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks. In this paper, we investigate simple, yet effective approaches for adapting the pre-trained foundation models to the downstream task of interest, namely, open-vocabulary semantic segmentation. To this end, we make the following contributions: (i) we introduce Fusioner, with a lightweight, transformer-based fusion module, that pairs the frozen visual representation with language concept through a handful of image segmentation data. As a consequence, the model gains the capability of zero-shot transfer to segment novel categories; (ii) without loss of generality, we experiment on a broad range of self-supervised models that have been pre-trained with different schemes, e.g. visual-only models (MoCo v3, DINO), language-only models (BERT), visual-language model (CLIP), and show that, the proposed fusion approach is effective to any pair of visual and language models, even those pre-trained on a corpus of uni-modal data; (iii) we conduct thorough ablation studies to analyze the critical components in our proposed Fusioner, while evaluating on standard benchmarks, e.g. PASCAL-5i and COCO-20i , it surpasses existing state-of-the-art models by a large margin, despite only being trained on frozen visual and language features; (iv) to measure the model's robustness on learning visual-language correspondence, we further evaluate on synthetic dataset, named Mosaic-4, where images are constructed by mosaicking the samples from FSS-1000. Fusioner demonstrates superior performance over previous models.
Detecting occluded objects still remains a challenge for state-of-the-art object detectors. The objective of this work is to improve the detection for such objects, and thereby improve the overall performance of a modern object detector. To this end we make the following four contributions: (1) We propose a simple 'plugin' module for the detection head of two-stage object detectors to improve the recall of partially occluded objects. The module predicts a tri-layer of segmentation masks for the target object, the occluder and the occludee, and by doing so is able to better predict the mask of the target object. (2) We propose a scalable pipeline for generating training data for the module by using amodal completion of existing object detection and instance segmentation training datasets to establish occlusion relationships. (3) We also establish a COCO evaluation dataset to measure the recall performance of partially occluded and separated objects. (4) We show that the plugin module inserted into a two-stage detector can boost the performance significantly, by only fine-tuning the detection head, and with additional improvements if the entire architecture is fine-tuned. COCO results are reported for Mask R-CNN with Swin-T or Swin-S backbones, and Cascade Mask R-CNN with a Swin-B backbone.
The objective of this paper is audio-visual synchronisation of general videos 'in the wild'. For such videos, the events that may be harnessed for synchronisation cues may be spatially small and may occur only infrequently during a many seconds-long video clip, i.e. the synchronisation signal is 'sparse in space and time'. This contrasts with the case of synchronising videos of talking heads, where audio-visual correspondence is dense in both time and space. We make four contributions: (i) in order to handle longer temporal sequences required for sparse synchronisation signals, we design a multi-modal transformer model that employs 'selectors' to distil the long audio and visual streams into small sequences that are then used to predict the temporal offset between streams. (ii) We identify artefacts that can arise from the compression codecs used for audio and video and can be used by audio-visual models in training to artificially solve the synchronisation task. (iii) We curate a dataset with only sparse in time and space synchronisation signals; and (iv) the effectiveness of the proposed model is shown on both dense and sparse datasets quantitatively and qualitatively. Project page: v-iashin.github.io/SparseSync
The objective of this paper is an efficient training method for video tasks. We make three contributions: (1) We propose Turbo training, a simple and versatile training paradigm for Transformers on multiple video tasks. (2) We illustrate the advantages of Turbo training on action classification, video-language representation learning, and long-video activity classification, showing that Turbo training can largely maintain competitive performance while achieving almost 4X speed-up and significantly less memory consumption. (3) Turbo training enables long-schedule video-language training and end-to-end long-video training, delivering competitive or superior performance than previous works, which were infeasible to train under limited resources.
Existing models on super-resolution often specialized for one scale, fundamentally limiting their use in practical scenarios. In this paper, we aim to develop a general plugin that can be inserted into existing super-resolution models, conveniently augmenting their ability towards Arbitrary Resolution Image Scaling, thus termed ARIS. We make the following contributions: (i) we propose a transformer-based plugin module, which uses spatial coordinates as query, iteratively attend the low-resolution image feature through cross-attention, and output visual feature for the queried spatial location, resembling an implicit representation for images; (ii) we introduce a novel self-supervised training scheme, that exploits consistency constraints to effectively augment the model's ability for upsampling images towards unseen scales, i.e. ground-truth high-resolution images are not available; (iii) without loss of generality, we inject the proposed ARIS plugin module into several existing models, namely, IPT, SwinIR, and HAT, showing that the resulting models can not only maintain their original performance on fixed scale factor but also extrapolate to unseen scales, substantially outperforming existing any-scale super-resolution models on standard benchmarks, e.g. Urban100, DIV2K, etc.