Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians' interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a generalized-mean (GeM) pooling followed by L2 normalization to classify lesion types and retrieve similar images before clinicians' analysis. Results have shown improved performance. We additionally build an open-source application for image analysis and retrieval. The application is easy to integrate, relieving manual efforts and suggesting the potential to support clinicians' everyday activities.
Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied on the recently spotlighted vision transformers (ViT), either require a large number of time steps or fail to converge. Based on analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each ViT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional ViTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and ImageNet with different ViT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10.
Active recognition, which allows intelligent agents to explore observations for better recognition performance, serves as a prerequisite for various embodied AI tasks, such as grasping, navigation and room arrangements. Given the evolving environment and the multitude of object classes, it is impractical to include all possible classes during the training stage. In this paper, we aim at advancing active open-vocabulary recognition, empowering embodied agents to actively perceive and classify arbitrary objects. However, directly adopting recent open-vocabulary classification models, like Contrastive Language Image Pretraining (CLIP), poses its unique challenges. Specifically, we observe that CLIP's performance is heavily affected by the viewpoint and occlusions, compromising its reliability in unconstrained embodied perception scenarios. Further, the sequential nature of observations in agent-environment interactions necessitates an effective method for integrating features that maintains discriminative strength for open-vocabulary classification. To address these issues, we introduce a novel agent for active open-vocabulary recognition. The proposed method leverages inter-frame and inter-concept similarities to navigate agent movements and to fuse features, without relying on class-specific knowledge. Compared to baseline CLIP model with 29.6% accuracy on ShapeNet dataset, the proposed agent could achieve 53.3% accuracy for open-vocabulary recognition, without any fine-tuning to the equipped CLIP model. Additional experiments conducted with the Habitat simulator further affirm the efficacy of our method.
While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals. Although vision-language models (VLMs) integrate LLM modules (1) aligned with static image features, and (2) may possess prior knowledge of world dynamics (as demonstrated in the text world), they have not been trained in an embodied visual world and thus cannot align with its dynamics. On the other hand, training an embodied agent in a noisy visual world without expert guidance is often challenging and inefficient. In this paper, we train a VLM agent living in a visual world using an LLM agent excelling in a parallel text world (but inapplicable to the visual world). Specifically, we distill LLM's reflection outcomes (improved actions by analyzing mistakes) in a text world's tasks to finetune the VLM on the same tasks of the visual world, resulting in an Embodied Multi-Modal Agent (EMMA) quickly adapting to the visual world dynamics. Such cross-modality imitation learning between the two parallel worlds enables EMMA to generalize to a broad scope of new tasks without any further guidance from the LLM expert. Extensive evaluations on the ALFWorld benchmark highlight EMMA's superior performance to SOTA VLM-based agents across diverse tasks, e.g., 20%-70% improvement in the success rate.
In this work, we show that text-to-image generative models can be 'inverted' to assess their own text-image understanding capabilities in a completely automated manner. Our method, called SelfEval, uses the generative model to compute the likelihood of real images given text prompts, making the generative model directly applicable to discriminative tasks. Using SelfEval, we repurpose standard datasets created for evaluating multimodal text-image discriminative models to evaluate generative models in a fine-grained manner: assessing their performance on attribute binding, color recognition, counting, shape recognition, spatial understanding. To the best of our knowledge SelfEval is the first automated metric to show a high degree of agreement for measuring text-faithfulness with the gold-standard human evaluations across multiple models and benchmarks. Moreover, SelfEval enables us to evaluate generative models on challenging tasks such as Winoground image-score where they demonstrate competitive performance to discriminative models. We also show severe drawbacks of standard automated metrics such as CLIP-score to measure text faithfulness on benchmarks such as DrawBench, and how SelfEval sidesteps these issues. We hope SelfEval enables easy and reliable automated evaluation for diffusion models.
Segment Anything Model (SAM) achieves remarkable results in 2D image segmentation of natural images. However, the huge gap between medical images and natural images prevents it directly applied to medical image segmentation tasks. Especially in 3D medical image, SAM cannot learn the contextual relationship between slices, which limites application in real scenarios. In addition, recent research shows that applying 2D SAM to 3D images requires prompting the entire volume, which is time and label comsuming. In order to solve the above problems, we introduced Slide-SAM which extended SAM to 3D medical images. Specifically, you only need to use a single slice prompt to segement the entire volume, which greatly reduces the prompt workload for professionals. Secondly, unlike traditional 3D medical image segmentation, we are free from the influence of computing resources and can still use high resolution (H$ \times $W = 1024$ \times $1024) for training in 3D images to achieve optimal learning for small targets. This is to combine the entire 3D volume is beyond the reach of training. Finally, we collected a large number of 3D images from large-scale 3D public and private datasets, and extended SAM to 3D medical image segmentation involving bounding box and point prompts. Finally, we perform a comprehensive evaluation and analysis investigating the performance of Slide-SAM in medical image segmentation of different modalities, anatomy, and organs. We have verified Slide-SAM's segmentation capabilities on multiple datasets, achieving the most advanced 3D segmentation performance while maintaining the minimum prompt. Code will be open source soon.
The domain adaptation approach has gained significant acceptance in transferring styles across various vendors and centers, along with filling the gaps in modalities. However, multi-center application faces the challenge of the difficulty of domain adaptation due to their intra-domain differences. We focus on introducing a fine-grained unsupervised framework for domain adaptation to facilitate cross-modality segmentation of vestibular schwannoma (VS) and cochlea. We propose to use a vector to control the generator to synthesize a fake image with given features. And then, we can apply various augmentations to the dataset by searching the feature dictionary. The diversity augmentation can increase the performance and robustness of the segmentation model. On the CrossMoDA validation phase Leaderboard, our method received a mean Dice score of 0.765 and 0.836 on VS and cochlea, respectively.
Interactive Segmentation Models (ISMs) like the Segment Anything Model have significantly improved various computer vision tasks, yet their application to Person Re-identification (ReID) remains limited. On the other hand, existing semantic pre-training models for ReID often have limitations like predefined parsing ranges or coarse semantics. Additionally, ReID and Clothes-Changing ReID (CC-ReID) are usually treated separately due to their different domains. This paper investigates whether utilizing precise human-centric semantic representation can boost the ReID performance and improve the generalization among various ReID tasks. We propose SemReID, a self-supervised ReID model that leverages ISMs for adaptive part-based semantic extraction, contributing to the improvement of ReID performance. SemReID additionally refines its semantic representation through techniques such as image masking and KoLeo regularization. Evaluation across three types of ReID datasets -- standard ReID, CC-ReID, and unconstrained ReID -- demonstrates superior performance compared to state-of-the-art methods. In addition, recognizing the scarcity of large person datasets with fine-grained semantics, we introduce the novel LUPerson-Part dataset to assist ReID methods in acquiring the fine-grained part semantics for robust performance.
In the field of computer graphics, the use of vector graphics, particularly Scalable Vector Graphics (SVG), represents a notable development from traditional pixel-based imagery. SVGs, with their XML-based format, are distinct in their ability to directly and explicitly represent visual elements such as shape, color, and path. This direct representation facilitates a more accurate and logical depiction of graphical elements, enhancing reasoning and interpretability. Recognizing the potential of SVGs, the machine learning community has introduced multiple methods for image vectorization. However, transforming images into SVG format while retaining the relational properties and context of the original scene remains a key challenge. Most vectorization methods often yield SVGs that are overly complex and not easily interpretable. In response to this challenge, we introduce our method, Simple-SVG-Generation (S\textsuperscript{2}VG\textsuperscript{2}). Our method focuses on producing SVGs that are both accurate and simple, aligning with human readability and understanding. With simple images, we evaluate our method with reasoning tasks together with advanced language models, the results show a clear improvement over previous SVG generation methods. We also conducted surveys for human evaluation on the readability of our generated SVGs, the results also favor our methods.
Dataset distillation reduces the storage and computational consumption of training a network by generating a small surrogate dataset that encapsulates rich information of the original large-scale one. However, previous distillation methods heavily rely on the sample-wise iterative optimization scheme. As the images-per-class (IPC) setting or image resolution grows larger, the necessary computation will demand overwhelming time and resources. In this work, we intend to incorporate generative diffusion techniques for computing the surrogate dataset. Observing that key factors for constructing an effective surrogate dataset are representativeness and diversity, we design additional minimax criteria in the generative training to enhance these facets for the generated images of diffusion models. We present a theoretical model of the process as hierarchical diffusion control demonstrating the flexibility of the diffusion process to target these criteria without jeopardizing the faithfulness of the sample to the desired distribution. The proposed method achieves state-of-the-art validation performance while demanding much less computational resources. Under the 100-IPC setting on ImageWoof, our method requires less than one-twentieth the distillation time of previous methods, yet yields even better performance. Source code available in https://github.com/vimar-gu/MinimaxDiffusion.