CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification

Alzheimer's disease (AD) is an incurable neurodegenerative condition leading to cognitive and functional deterioration. Given the lack of a cure, prompt and precise AD diagnosis is vital, a complex process dependent on multiple factors and multi-modal data. While successful efforts have been made to integrate multi-modal representation learning into medical datasets, scant attention has been given to 3D medical images. In this paper, we propose Contrastive Masked Vim Autoencoder (CMViM), the first efficient representation learning method tailored for 3D multi-modal data. Our proposed framework is built on a masked Vim autoencoder to learn a unified multi-modal representation and long-dependencies contained in 3D medical images. We also introduce an intra-modal contrastive learning module to enhance the capability of the multi-modal Vim encoder for modeling the discriminative features in the same modality, and an inter-modal contrastive learning module to alleviate misaligned representation among modalities. Our framework consists of two main steps: 1) incorporate the Vision Mamba (Vim) into the mask autoencoder to reconstruct 3D masked multi-modal data efficiently. 2) align the multi-modal representations with contrastive learning mechanisms from both intra-modal and inter-modal aspects. Our framework is pre-trained and validated ADNI2 dataset and validated on the downstream task for AD classification. The proposed CMViM yields 2.7\% AUC performance improvement compared with other state-of-the-art methods.

BiSVP: Building Footprint Extraction via Bidirectional Serialized Vertex Prediction

Extracting building footprints from remote sensing images has been attracting extensive attention recently. Dominant approaches address this challenging problem by generating vectorized building masks with cumbersome refinement stages, which limits the application of such methods. In this paper, we introduce a new refinement-free and end-to-end building footprint extraction method, which is conceptually intuitive, simple, and effective. Our method, termed as BiSVP, represents a building instance with ordered vertices and formulates the building footprint extraction as predicting the serialized vertices directly in a bidirectional fashion. Moreover, we propose a cross-scale feature fusion (CSFF) module to facilitate high resolution and rich semantic feature learning, which is essential for the dense building vertex prediction task. Without bells and whistles, our BiSVP outperforms state-of-the-art methods by considerable margins on three building instance segmentation benchmarks, clearly demonstrating its superiority. The code and datasets will be made public available.

Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous knowledge, because the teacher is updated with the past student only. To alleviate this problem, we propose a novel self-training strategy, which allows the model to learn from the future. Concretely, at each training step, we first virtually optimize the student (i.e., caching the gradients without applying them to the model weights), then update the teacher with the virtual future student, and finally ask the teacher to produce pseudo-labels for the current student as the guidance. In this way, we manage to improve the quality of pseudo-labels and thus boost the performance. We also develop two variants of our future-self-training (FST) framework through peeping at the future both deeply (FST-D) and widely (FST-W). Taking the tasks of unsupervised domain adaptive semantic segmentation and semi-supervised semantic segmentation as the instances, we experimentally demonstrate the effectiveness and superiority of our approach under a wide range of settings. Code will be made publicly available.

Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Map (CAM) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to generate more complete and precise pseudo masks for segmentation. In this study, we explore two implicit but intuitive constraints, i.e., cross-view feature semantic consistency and intra(inter)-class compactness(dispersion), to narrow the supervision gap. To this end, we propose two novel pixel-to-prototype contrast regularization terms that are conducted cross different views and within per single view of an image, respectively. Besides, we adopt two sample mining strategies, named semi-hard prototype mining and hard pixel sampling, to better leverage hard examples while reducing incorrect contrasts caused due to the absence of precise pixel-wise labels. Our method can be seamlessly incorporated into existing WSSS models without any changes to the base network and does not incur any extra inference burden. Experiments on standard benchmark show that our method consistently improves two strong baselines by large margins, demonstrating the effectiveness of our method. Specifically, built on top of SEAM, we improve the initial seed mIoU on PASCAL VOC 2012 from 55.4% to 61.5%. Moreover, armed with our method, we increase the segmentation mIoU of EPS from 70.8% to 73.6%, achieving new state-of-the-art.

Visual Grounding with Transformers

In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage detector by fusing textual embeddings, our approach is built on top of a transformer encoder-decoder and is independent of any pretrained detectors or word embedding models. Termed VGTR -- Visual Grounding with TRansformers, our approach is designed to learn semantic-discriminative visual features under the guidance of the textual description without harming their location ability. This information flow enables our VGTR to have a strong capability in capturing context-level semantics of both vision and language modalities, rendering us to aggregate accurate visual clues implied by the description to locate the interested object instance. Experiments show that our method outperforms state-of-the-art proposal-free approaches by a considerable margin on five benchmarks while maintaining fast inference speed.

Variance Loss: A Confidence-Based Reweighting Strategy for Coarse Semantic Segmentation

Coarsely-labeled semantic segmentation annotations are easy to obtain, but therefore bear the risk of losing edge details and introducing background noise. Though they are usually used as a supplement to the finely-labeled ones, in this paper, we attempt to train a model only using these coarse annotations, and improve the model performance with a noise-robust reweighting strategy. Specifically, the proposed confidence indicator makes it possible to design a reweighting strategy that simultaneously mines hard samples and alleviates noisy labels for the coarse annotation. Besides, the optimal reweighting strategy can be automatically derived by our Adversarial Weight Assigning Module (AWAM) with only 53 learnable parameters. Moreover, a rigorous proof of the convergence of AWAM is given. Experiments on standard datasets show that our proposed reweighting strategy can bring consistent performance improvements for both coarse annotations and fine annotations. In particular, built on top of DeeplabV3+, we improve the mIoU on Cityscapes Coarse dataset (coarsely-labeled) and ADE20K (finely-labeled) by 2.21 and 0.91, respectively.