The task of Split and Rephrase, which splits a complex sentence into multiple simple sentences with the same meaning, improves readability and enhances the performance of downstream tasks in natural language processing (NLP). However, while Split and Rephrase can be improved using a text-to-text generation approach that applies encoder-decoder models fine-tuned with a large-scale dataset, it still suffers from hallucinations and under-splitting. To address these issues, this paper presents a simple and strong data refinement approach. Here, we create WikiSplit++ by removing instances in WikiSplit where complex sentences do not entail at least one of the simpler sentences and reversing the order of reference simple sentences. Experimental results show that training with WikiSplit++ leads to better performance than training with WikiSplit, even with fewer training instances. In particular, our approach yields significant gains in the number of splits and the entailment ratio, a proxy for measuring hallucinations.
Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy. To address this, advanced deep learning-based LDCT denoising algorithms have been developed, primarily using Convolutional Neural Networks (CNNs) or Transformer Networks with the Unet architecture. This architecture enhances image detail by integrating feature maps from the encoder and decoder via skip connections. However, current methods often overlook enhancements to the Unet architecture itself, focusing instead on optimizing encoder and decoder structures. This approach can be problematic due to the significant differences in feature map characteristics between the encoder and decoder, where simple fusion strategies may not effectively reconstruct images.In this paper, we introduce WiTUnet, a novel LDCT image denoising method that utilizes nested, dense skip pathways instead of traditional skip connections to improve feature integration. WiTUnet also incorporates a windowed Transformer structure to process images in smaller, non-overlapping segments, reducing computational load. Additionally, the integration of a Local Image Perception Enhancement (LiPe) module in both the encoder and decoder replaces the standard multi-layer perceptron (MLP) in Transformers, enhancing local feature capture and representation. Through extensive experimental comparisons, WiTUnet has demonstrated superior performance over existing methods in key metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Root Mean Square Error (RMSE), significantly improving noise removal and image quality.
Scanning real-life scenes with modern registration devices typically gives incomplete point cloud representations, primarily due to the limitations of partial scanning, 3D occlusions, and dynamic light conditions. Recent works on processing incomplete point clouds have always focused on point cloud completion. However, these approaches do not ensure consistency between the completed point cloud and the captured images regarding color and geometry. We propose using Generative Point-based NeRF (GPN) to reconstruct and repair a partial cloud by fully utilizing the scanning images and the corresponding reconstructed cloud. The repaired point cloud can achieve multi-view consistency with the captured images at high spatial resolution. For the finetunes of a single scene, we optimize the global latent condition by incorporating an Auto-Decoder architecture while retaining multi-view consistency. As a result, the generated point clouds are smooth, plausible, and geometrically consistent with the partial scanning images. Extensive experiments on ShapeNet demonstrate that our works achieve competitive performances to the other state-of-the-art point cloud-based neural scene rendering and editing performances.
Large Language Models (LLMs) have achieved remarkable performance across various natural language processing tasks, primarily due to the transformer architecture and its self-attention mechanism. However, we observe that in standard decoder-style LLMs, attention matrices degenerate to single-column for deeper layers. Layers in this state are unable to learn anything meaningful and mostly redundant; we refer to these as lazy layers. The goal of this paper is to train smaller models by eliminating this structural inefficiency without compromising performance. Motivated by this observation, we propose Inheritune, a simple yet effective training recipe for developing smaller, high-performing language models. Smaller models trained with Inheritune, inherit early transformer layers from a larger pre-trained model, then retrain and progressively expand until they match or exceed the performance of the larger model. We demonstrate that Inheritune enables the training of various sizes of GPT-2 models on datasets like OpenWebText-9B and FineWeb_edu. Models trained with Inheritune, despite having significantly fewer layers, match or even surpass the performance of their larger counterparts. For instance, our 16-layer GPT-2 medium variant achieves comparable performance to the standard 24-layer GPT-2 medium model. Code is available at https://github.com/sanyalsunny111/LLM-Inheritune.
As a vital component in autonomous driving, accurate trajectory prediction effectively prevents traffic accidents and improves driving efficiency. To capture complex spatial-temporal dynamics and social interactions, recent studies developed models based on advanced deep-learning methods. On the other hand, recent studies have explored the use of deep generative models to further account for trajectory uncertainties. However, the current approaches demonstrating indeterminacy involve inefficient and time-consuming practices such as sampling from trained models. To fill this gap, we proposed a novel model named Graph Recurrent Attentive Neural Process (GRANP) for vehicle trajectory prediction while efficiently quantifying prediction uncertainty. In particular, GRANP contains an encoder with deterministic and latent paths, and a decoder for prediction. The encoder, including stacked Graph Attention Networks, LSTM and 1D convolutional layers, is employed to extract spatial-temporal relationships. The decoder is used to learn a latent distribution and thus quantify prediction uncertainty. To reveal the effectiveness of our model, we evaluate the performance of GRANP on the highD dataset. Extensive experiments show that GRANP achieves state-of-the-art results and can efficiently quantify uncertainties. Additionally, we undertake an intuitive case study that showcases the interpretability of the proposed approach. The code is available at https://github.com/joy-driven/GRANP.
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a multitasking problem of event localization and event captioning to consider inter-task relations. However, addressing both tasks using only visual input is challenging due to the lack of semantic content. In this study, we address this by proposing a novel framework inspired by the cognitive information processing of humans. Our model utilizes external memory to incorporate prior knowledge. The memory retrieval method is proposed with cross-modal video-to-text matching. To effectively incorporate retrieved text features, the versatile encoder and the decoder with visual and textual cross-attention modules are designed. Comparative experiments have been conducted to show the effectiveness of the proposed method on ActivityNet Captions and YouCook2 datasets. Experimental results show promising performance of our model without extensive pretraining from a large video dataset.
Dichotomous Image Segmentation (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. When designing an effective DIS model, the main challenge is how to balance the semantic dispersion of high-resolution targets in the small receptive field and the loss of high-precision details in the large receptive field. Existing methods rely on tedious multiple encoder-decoder streams and stages to gradually complete the global localization and local refinement. Human visual system captures regions of interest by observing them from multiple views. Inspired by it, we model DIS as a multi-view object perception problem and provide a parsimonious multi-view aggregation network (MVANet), which unifies the feature fusion of the distant view and close-up view into a single stream with one encoder-decoder structure. With the help of the proposed multi-view complementary localization and refinement modules, our approach established long-range, profound visual interactions across multiple views, allowing the features of the detailed close-up view to focus on highly slender structures.Experiments on the popular DIS-5K dataset show that our MVANet significantly outperforms state-of-the-art methods in both accuracy and speed. The source code and datasets will be publicly available at \href{https://github.com/qianyu-dlut/MVANet}{MVANet}.
This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a causal mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training. We suggest to reposition the class token behind the image tokens with a post-sequence class token technique to overcome this challenge, enabling causal self-attention to efficiently capture the entire image's information. Additionally, we develop a soft mask strategy that gradually introduces a causal mask to the self-attention at the onset of training to facilitate the optimization behavior. The tailored model, dubbed as image LLaMA (iLLaMA), is akin to LLaMA in architecture and enables direct supervised learning. Its causal self-attention boosts computational efficiency and learns complex representation by elevating attention map ranks. iLLaMA rivals the performance with its encoder-only counterparts, achieving 75.1% ImageNet top-1 accuracy with only 5.7M parameters. Scaling the model to $\sim$310M and pre-training on ImageNet-21K further enhances the accuracy to 86.0%. Extensive experiments demonstrate iLLaMA's reliable properties: shape-texture bias, calibration, quantization compatibility, ADE20K segmentation and CIFAR transfer learning. We hope our study can kindle fresh views to visual architectures in the wave of LLMs and inspire the development of unified multimodal models. Pre-trained models and codes are available https://github.com/techmonsterwang/iLLaMA.
Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity. Mamba-based models, with their superior long-range modeling and linear efficiency, have garnered substantial attention. This study pioneers the application of Mamba to multi-class unsupervised anomaly detection, presenting MambaAD, which consists of a pre-trained encoder and a Mamba decoder featuring (Locality-Enhanced State Space) LSS modules at multi-scales. The proposed LSS module, integrating parallel cascaded (Hybrid State Space) HSS blocks and multi-kernel convolutions operations, effectively captures both long-range and local information. The HSS block, utilizing (Hybrid Scanning) HS encoders, encodes feature maps into five scanning methods and eight directions, thereby strengthening global connections through the (State Space Model) SSM. The use of Hilbert scanning and eight directions significantly improves feature sequence modeling. Comprehensive experiments on six diverse anomaly detection datasets and seven metrics demonstrate state-of-the-art performance, substantiating the method's effectiveness.
We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation. The JPEG algorithm significantly quantizes discrete cosine transform (DCT) spectra to achieve a high compression rate, inevitably resulting in quality degradation while encoding an image. We have designed a continuous cosine spectrum estimator to address the quality degradation issue that restores the distorted spectrum. By leveraging local DCT formulations, our network has the privilege to exploit dequantization and upsampling simultaneously. Our proposed model enables decoding compressed images directly across different quality factors using a single pre-trained model without relying on a conventional JPEG decoder. As a result, our proposed network achieves state-of-the-art performance in flexible color image JPEG artifact removal tasks. Our source code is available at https://github.com/WooKyoungHan/JDEC.
The embedding-based retrieval (EBR) approach is widely used in mainstream search engine retrieval systems and is crucial in recent retrieval-augmented methods for eliminating LLM illusions. However, existing EBR models often face the "semantic drift" problem and insufficient focus on key information, leading to a low adoption rate of retrieval results in subsequent steps. This issue is especially noticeable in real-time search scenarios, where the various expressions of popular events on the Internet make real-time retrieval heavily reliant on crucial event information. To tackle this problem, this paper proposes a novel approach called EER, which enhances real-time retrieval performance by improving the dual-encoder model of traditional EBR. We incorporate contrastive learning to accompany pairwise learning for encoder optimization. Furthermore, to strengthen the focus on critical event information in events, we include a decoder module after the document encoder, introduce a generative event triplet extraction scheme based on prompt-tuning, and correlate the events with query encoder optimization through comparative learning. This decoder module can be removed during inference. Extensive experiments demonstrate that EER can significantly improve the real-time search retrieval performance. We believe that this approach will provide new perspectives in the field of information retrieval. The codes and dataset are available at https://github.com/open-event-hub/Event-enhanced_Retrieval .
Large decoder-only language models (LLMs) are the state-of-the-art models on most of today's NLP tasks and benchmarks. Yet, the community is only slowly adopting these models for text embedding tasks, which require rich contextualized representations. In this work, we introduce LLM2Vec, a simple unsupervised approach that can transform any decoder-only LLM into a strong text encoder. LLM2Vec consists of three simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. We demonstrate the effectiveness of LLM2Vec by applying it to 4 popular LLMs ranging from 1.3B to 8B parameters and evaluate the transformed models on English word- and sequence-level tasks. We outperform encoder-only models by a large margin on word-level tasks and reach a new unsupervised state-of-the-art performance on the Massive Text Embeddings Benchmark (MTEB). Moreover, when combining LLM2Vec with supervised contrastive learning, we achieve state-of-the-art performance on MTEB among models that train only on publicly available data (as of May 24, 2024). Our strong empirical results and extensive analysis demonstrate that LLMs can be effectively transformed into universal text encoders in a parameter-efficient manner without the need for expensive adaptation or synthetic GPT-4 generated data.
Single-pixel imaging (SPI) is a potential computational imaging technique which produces image by solving an illposed reconstruction problem from few measurements captured by a single-pixel detector. Deep learning has achieved impressive success on SPI reconstruction. However, previous poor reconstruction performance and impractical imaging model limit its real-world applications. In this paper, we propose a deep unfolding network with hybrid-attention Transformer on Kronecker SPI model, dubbed HATNet, to improve the imaging quality of real SPI cameras. Specifically, we unfold the computation graph of the iterative shrinkagethresholding algorithm (ISTA) into two alternative modules: efficient tensor gradient descent and hybrid-attention multiscale denoising. By virtue of Kronecker SPI, the gradient descent module can avoid high computational overheads rooted in previous gradient descent modules based on vectorized SPI. The denoising module is an encoder-decoder architecture powered by dual-scale spatial attention for high- and low-frequency aggregation and channel attention for global information recalibration. Moreover, we build a SPI prototype to verify the effectiveness of the proposed method. Extensive experiments on synthetic and real data demonstrate that our method achieves the state-of-the-art performance. The source code and pre-trained models are available at https://github.com/Gang-Qu/HATNet-SPI.
Recently, diffusion models (DM) have been applied in magnetic resonance imaging (MRI) super-resolution (SR) reconstruction, exhibiting impressive performance, especially with regard to detailed reconstruction. However, the current DM-based SR reconstruction methods still face the following issues: (1) They require a large number of iterations to reconstruct the final image, which is inefficient and consumes a significant amount of computational resources. (2) The results reconstructed by these methods are often misaligned with the real high-resolution images, leading to remarkable distortion in the reconstructed MR images. To address the aforementioned issues, we propose an efficient diffusion model for multi-contrast MRI SR, named as DiffMSR. Specifically, we apply DM in a highly compact low-dimensional latent space to generate prior knowledge with high-frequency detail information. The highly compact latent space ensures that DM requires only a few simple iterations to produce accurate prior knowledge. In addition, we design the Prior-Guide Large Window Transformer (PLWformer) as the decoder for DM, which can extend the receptive field while fully utilizing the prior knowledge generated by DM to ensure that the reconstructed MR image remains undistorted. Extensive experiments on public and clinical datasets demonstrate that our DiffMSR outperforms state-of-the-art methods.
For a unified analysis of medical images from different modalities, data harmonization using image-to-image (I2I) translation is desired. We study this problem employing an optical coherence tomography (OCT) data set of Spectralis-OCT and Home-OCT images. I2I translation is challenging because the images are unpaired, and a bijective mapping does not exist due to the information discrepancy between both domains. This problem has been addressed by the Contrastive Learning for Unpaired I2I Translation (CUT) approach, but it reduces semantic consistency. To restore the semantic consistency, we support the style decoder using an additional segmentation decoder. Our approach increases the similarity between the style-translated images and the target distribution. Importantly, we improve the segmentation of biomarkers in Home-OCT images in an unsupervised domain adaptation scenario. Our data harmonization approach provides potential for the monitoring of diseases, e.g., age related macular disease, using different OCT devices.
In this paper, we introduce T-DEED, a Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in sports videos. T-DEED addresses multiple challenges in the task, including the need for discriminability among frame representations, high output temporal resolution to maintain prediction precision, and the necessity to capture information at different temporal scales to handle events with varying dynamics. It tackles these challenges through its specifically designed architecture, featuring an encoder-decoder for leveraging multiple temporal scales and achieving high output temporal resolution, along with temporal modules designed to increase token discriminability. Leveraging these characteristics, T-DEED achieves SOTA performance on the FigureSkating and FineDiving datasets. Code is available at https://github.com/arturxe2/T-DEED.
Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses to naturalistic images that have not been manipulated to test hypotheses regarding how DNNs or humans perceive and identify objects. Here we introduce the toolbox MindSet: Vision, consisting of a collection of image datasets and related scripts designed to test DNNs on 30 psychological findings. In all experimental conditions, the stimuli are systematically manipulated to test specific hypotheses regarding human visual perception and object recognition. In addition to providing pre-generated datasets of images, we provide code to regenerate these datasets, offering many configurable parameters which greatly extend the dataset versatility for different research contexts, and code to facilitate the testing of DNNs on these image datasets using three different methods (similarity judgments, out-of-distribution classification, and decoder method), accessible at https://github.com/MindSetVision/mindset-vision. We test ResNet-152 on each of these methods as an example of how the toolbox can be used.
This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval. We build on previous research that demonstrated loss of information in the middle of input sequences for causal language models, extending it to the domain of representation learning. We examine positional biases at various stages of training for an encoder-decoder model, including language model pre-training, contrastive pre-training, and contrastive fine-tuning. Experiments with the MS-MARCO document collection reveal that after contrastive pre-training the model already generates embeddings that better capture early contents of the input, with fine-tuning further aggravating this effect.
Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environments. Leveraging additional modalities (X-modality) like thermal and depth alongside traditional RGB provides complementary information, enabling more robust and reliable prediction. In this work, we introduce Sigma, a Siamese Mamba network for multi-modal semantic segmentation utilizing the advanced Mamba. Unlike conventional methods that rely on CNNs, with their limited local receptive fields, or Vision Transformers (ViTs), which offer global receptive fields at the cost of quadratic complexity, our model achieves global receptive fields with linear complexity. By employing a Siamese encoder and innovating a Mamba-based fusion mechanism, we effectively select essential information from different modalities. A decoder is then developed to enhance the channel-wise modeling ability of the model. Our proposed method is rigorously evaluated on both RGB-Thermal and RGB-Depth semantic segmentation tasks, demonstrating its superiority and marking the first successful application of State Space Models (SSMs) in multi-modal perception tasks. Code is available at https://github.com/zifuwan/Sigma.
Robust, faithful and harm-free pronoun use for individuals is an important goal for language model development as their use increases, but prior work tends to study only one or two of these characteristics at a time. To measure progress towards the combined goal, we introduce the task of pronoun fidelity: given a context introducing a co-referring entity and pronoun, the task is to reuse the correct pronoun later. We present RUFF, a carefully-designed dataset of over 5 million instances to measure robust pronoun fidelity in English, and we evaluate 37 model variants from nine popular families, across architectures (encoder-only, decoder-only and encoder-decoder) and scales (11M-70B parameters). When an individual is introduced with a pronoun, models can mostly faithfully reuse this pronoun in the next sentence, but they are significantly worse with she/her/her, singular they and neopronouns. Moreover, models are easily distracted by non-adversarial sentences discussing other people; even one sentence with a distractor pronoun causes accuracy to drop on average by 34 percentage points. Our results show that pronoun fidelity is not robust, in a simple, naturalistic setting where humans achieve nearly 100% accuracy. We encourage researchers to bridge the gaps we find and to carefully evaluate reasoning in settings where superficial repetition might inflate perceptions of model performance.