Large language models reveal deep comprehension and fluent generation in the field of multi-modality. Although significant advancements have been achieved in audio multi-modality, existing methods are rarely leverage language model for sound event detection (SED). In this work, we propose an end-to-end framework for understanding audio features while simultaneously generating sound event and their temporal location. Specifically, we employ pretrained acoustic models to capture discriminative features across different categories and language models for autoregressive text generation. Conventional methods generally struggle to obtain features in pure audio domain for classification. In contrast, our framework utilizes the language model to flexibly understand abundant semantic context aligned with the acoustic representation. The experimental results showcase the effectiveness of proposed method in enhancing timestamps precision and event classification.
The goal of sequential recommendation (SR) is to predict a user's potential interested items based on her/his historical interaction sequences. Most existing sequential recommenders are developed based on ID features, which, despite their widespread use, often underperform with sparse IDs and struggle with the cold-start problem. Besides, inconsistent ID mappings hinder the model's transferability, isolating similar recommendation domains that could have been co-optimized. This paper aims to address these issues by exploring the potential of multi-modal information in learning robust and generalizable sequence representations. We propose MISSRec, a multi-modal pre-training and transfer learning framework for SR. On the user side, we design a Transformer-based encoder-decoder model, where the contextual encoder learns to capture the sequence-level multi-modal user interests while a novel interest-aware decoder is developed to grasp item-modality-interest relations for better sequence representation. On the candidate item side, we adopt a dynamic fusion module to produce user-adaptive item representation, providing more precise matching between users and items. We pre-train the model with contrastive learning objectives and fine-tune it in an efficient manner. Extensive experiments demonstrate the effectiveness and flexibility of MISSRec, promising a practical solution for real-world recommendation scenarios. Data and code are available on \url{https://github.com/gimpong/MM23-MISSRec}.
We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being constrained by fixed label spaces) is crucial for many real-world vision tasks. Contrastive pre-training on large image-text datasets has recently led to significant improvements for image-level tasks. For more structured tasks involving object localization applying pre-trained models is more challenging. This is particularly true for video tasks, where task-specific data is limited. We show successful transfer of open-world models by building on the OWL-ViT open-vocabulary detection model and adapting it to video by adding a transformer decoder. The decoder propagates object representations recurrently through time by using the output tokens for one frame as the object queries for the next. Our model is end-to-end trainable on video data and enjoys improved temporal consistency compared to tracking-by-detection baselines, while retaining the open-world capabilities of the backbone detector. We evaluate our model on the challenging TAO-OW benchmark and demonstrate that open-world capabilities, learned from large-scale image-text pre-training, can be transferred successfully to open-world localization across diverse videos.
We present TokenSplit, a speech separation model that acts on discrete token sequences. The model is trained on multiple tasks simultaneously: separate and transcribe each speech source, and generate speech from text. The model operates on transcripts and audio token sequences and achieves multiple tasks through masking of inputs. The model is a sequence-to-sequence encoder-decoder model that uses the Transformer architecture. We also present a "refinement" version of the model that predicts enhanced audio tokens from the audio tokens of speech separated by a conventional separation model. Using both objective metrics and subjective MUSHRA listening tests, we show that our model achieves excellent performance in terms of separation, both with or without transcript conditioning. We also measure the automatic speech recognition (ASR) performance and provide audio samples of speech synthesis to demonstrate the additional utility of our model.
Watermarking serves as a widely adopted approach to safeguard media copyright. In parallel, the research focus has extended to watermark removal techniques, offering an adversarial means to enhance watermark robustness and foster advancements in the watermarking field. Existing watermark removal methods mainly rely on UNet with task-specific decoder branches--one for watermark localization and the other for background image restoration. However, watermark localization and background restoration are not isolated tasks; precise watermark localization inherently implies regions necessitating restoration, and the background restoration process contributes to more accurate watermark localization. To holistically integrate information from both branches, we introduce an implicit joint learning paradigm. This empowers the network to autonomously navigate the flow of information between implicit branches through a gate mechanism. Furthermore, we employ cross-channel attention to facilitate local detail restoration and holistic structural comprehension, while harnessing nested structures to integrate multi-scale information. Extensive experiments are conducted on various challenging benchmarks to validate the effectiveness of our proposed method. The results demonstrate our approach's remarkable superiority, surpassing existing state-of-the-art methods by a large margin.
Glaucoma is an eye disease that causes damage to the optic nerve, which can lead to visual loss and permanent blindness. Early glaucoma detection is therefore critical in order to avoid permanent blindness. The estimation of the cup-to-disc ratio (CDR) during an examination of the optical disc (OD) is used for the diagnosis of glaucoma. In this paper, we present the EDDense-Net segmentation network for the joint segmentation of OC and OD. The encoder and decoder in this network are made up of dense blocks with a grouped convolutional layer in each block, allowing the network to acquire and convey spatial information from the image while simultaneously reducing the network's complexity. To reduce spatial information loss, the optimal number of filters in all convolution layers were utilised. In semantic segmentation, dice pixel classification is employed in the decoder to alleviate the problem of class imbalance. The proposed network was evaluated on two publicly available datasets where it outperformed existing state-of-the-art methods in terms of accuracy and efficiency. For the diagnosis and analysis of glaucoma, this method can be used as a second opinion system to assist medical ophthalmologists.
Spiking neural networks (SNNs) have tremendous potential for energy-efficient neuromorphic chips due to their binary and event-driven architecture. SNNs have been primarily used in classification tasks, but limited exploration on image generation tasks. To fill the gap, we propose a Spiking-Diffusion model, which is based on the vector quantized discrete diffusion model. First, we develop a vector quantized variational autoencoder with SNNs (VQ-SVAE) to learn a discrete latent space for images. In VQ-SVAE, image features are encoded using both the spike firing rate and postsynaptic potential, and an adaptive spike generator is designed to restore embedding features in the form of spike trains. Next, we perform absorbing state diffusion in the discrete latent space and construct a spiking diffusion image decoder (SDID) with SNNs to denoise the image. Our work is the first to build the diffusion model entirely from SNN layers. Experimental results on MNIST, FMNIST, KMNIST, Letters, and Cifar10 demonstrate that Spiking-Diffusion outperforms the existing SNN-based generation model. We achieve FIDs of 37.50, 91.98, 59.23, 67.41, and 120.5 on the above datasets respectively, with reductions of 58.60\%, 18.75\%, 64.51\%, 29.75\%, and 44.88\% in FIDs compared with the state-of-art work. Our code will be available at \url{https://github.com/Arktis2022/Spiking-Diffusion}.
This work proposes an end-to-end neural interactive keypoint detection framework named Click-Pose, which can significantly reduce more than 10 times labeling costs of 2D keypoint annotation compared with manual-only annotation. Click-Pose explores how user feedback can cooperate with a neural keypoint detector to correct the predicted keypoints in an interactive way for a faster and more effective annotation process. Specifically, we design the pose error modeling strategy that inputs the ground truth pose combined with four typical pose errors into the decoder and trains the model to reconstruct the correct poses, which enhances the self-correction ability of the model. Then, we attach an interactive human-feedback loop that allows receiving users' clicks to correct one or several predicted keypoints and iteratively utilizes the decoder to update all other keypoints with a minimum number of clicks (NoC) for efficient annotation. We validate Click-Pose in in-domain, out-of-domain scenes, and a new task of keypoint adaptation. For annotation, Click-Pose only needs 1.97 and 6.45 NoC@95 (at precision 95%) on COCO and Human-Art, reducing 31.4% and 36.3% efforts than the SOTA model (ViTPose) with manual correction, respectively. Besides, without user clicks, Click-Pose surpasses the previous end-to-end model by 1.4 AP on COCO and 3.0 AP on Human-Art. The code is available at https://github.com/IDEA-Research/Click-Pose.
The task of Human-Object Interaction (HOI) detection is to detect humans and their interactions with surrounding objects, where transformer-based methods show dominant advances currently. However, these methods ignore the relationship among humans, objects, and interactions: 1) human features are more contributive than object ones to interaction prediction; 2) interactive information disturbs the detection of objects but helps human detection. In this paper, we propose a Human and Object Disentangling Network (HODN) to model the HOI relationships explicitly, where humans and objects are first detected by two disentangling decoders independently and then processed by an interaction decoder. Considering that human features are more contributive to interaction, we propose a Human-Guide Linking method to make sure the interaction decoder focuses on the human-centric regions with human features as the positional embeddings. To handle the opposite influences of interactions on humans and objects, we propose a Stop-Gradient Mechanism to stop interaction gradients from optimizing the object detection but to allow them to optimize the human detection. Our proposed method achieves competitive performance on both the V-COCO and the HICO-Det datasets. It can be combined with existing methods easily for state-of-the-art results.
In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent advances in Transformer-based methods usually adopt an implicit synergy strategy with shared query, which can not fully realize the potential of these two interactive tasks. In this paper, we argue that the explicit synergy considering distinct characteristics of text detection and recognition can significantly improve the performance text spotting. To this end, we introduce a new model named Explicit Synergy-based Text Spotting Transformer framework (ESTextSpotter), which achieves explicit synergy by modeling discriminative and interactive features for text detection and recognition within a single decoder. Specifically, we decompose the conventional shared query into task-aware queries for text polygon and content, respectively. Through the decoder with the proposed vision-language communication module, the queries interact with each other in an explicit manner while preserving discriminative patterns of text detection and recognition, thus improving performance significantly. Additionally, we propose a task-aware query initialization scheme to ensure stable training. Experimental results demonstrate that our model significantly outperforms previous state-of-the-art methods. Code is available at https://github.com/mxin262/ESTextSpotter.
Animal visual perception is an important technique for automatically monitoring animal health, understanding animal behaviors, and assisting animal-related research. However, it is challenging to design a deep learning-based perception model that can freely adapt to different animals across various perception tasks, due to the varying poses of a large diversity of animals, lacking data on rare species, and the semantic inconsistency of different tasks. We introduce UniAP, a novel Universal Animal Perception model that leverages few-shot learning to enable cross-species perception among various visual tasks. Our proposed model takes support images and labels as prompt guidance for a query image. Images and labels are processed through a Transformer-based encoder and a lightweight label encoder, respectively. Then a matching module is designed for aggregating information between prompt guidance and the query image, followed by a multi-head label decoder to generate outputs for various tasks. By capitalizing on the shared visual characteristics among different animals and tasks, UniAP enables the transfer of knowledge from well-studied species to those with limited labeled data or even unseen species. We demonstrate the effectiveness of UniAP through comprehensive experiments in pose estimation, segmentation, and classification tasks on diverse animal species, showcasing its ability to generalize and adapt to new classes with minimal labeled examples.
Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. However, such models must be trained from scratch with specialised methods: therefore, access to a training dataset is required when the need for zero-shot classification arises. In this paper, we aim to equip pre-trained models with zero-shot classification capabilities without the use of image data. We achieve this with our proposed Image-free Classifier Injection with Semantics (ICIS) that injects classifiers for new, unseen classes into pre-trained classification models in a post-hoc fashion without relying on image data. Instead, the existing classifier weights and simple class-wise descriptors, such as class names or attributes, are used. ICIS has two encoder-decoder networks that learn to reconstruct classifier weights from descriptors (and vice versa), exploiting (cross-)reconstruction and cosine losses to regularise the decoding process. Notably, ICIS can be cheaply trained and applied directly on top of pre-trained classification models. Experiments on benchmark ZSL datasets show that ICIS produces unseen classifier weights that achieve strong (generalised) zero-shot classification performance. Code is available at https://github.com/ExplainableML/ImageFreeZSL .
Temporal Action Detection (TAD) is challenging but fundamental for real-world video applications. Recently, DETR-based models have been devised for TAD but have not performed well yet. In this paper, we point out the problem in the self-attention of DETR for TAD; the attention modules focus on a few key elements, called temporal collapse problem. It degrades the capability of the encoder and decoder since their self-attention modules play no role. To solve the problem, we propose a novel framework, Self-DETR, which utilizes cross-attention maps of the decoder to reactivate self-attention modules. We recover the relationship between encoder features by simple matrix multiplication of the cross-attention map and its transpose. Likewise, we also get the information within decoder queries. By guiding collapsed self-attention maps with the guidance map calculated, we settle down the temporal collapse of self-attention modules in the encoder and decoder. Our extensive experiments demonstrate that Self-DETR resolves the temporal collapse problem by keeping high diversity of attention over all layers.
Depth sensing is of paramount importance for unmanned aerial and autonomous vehicles. Nonetheless, contemporary monocular depth estimation methods employing complex deep neural networks within Convolutional Neural Networks are inadequately expedient for real-time inference on embedded platforms. This paper endeavors to surmount this challenge by proposing two efficient and lightweight architectures, RT-MonoDepth and RT-MonoDepth-S, thereby mitigating computational complexity and latency. Our methodologies not only attain accuracy comparable to prior depth estimation methods but also yield faster inference speeds. Specifically, RT-MonoDepth and RT-MonoDepth-S achieve frame rates of 18.4&30.5 FPS on NVIDIA Jetson Nano and 253.0&364.1 FPS on Jetson AGX Orin, utilizing a single RGB image of resolution 640x192. The experimental results underscore the superior accuracy and faster inference speed of our methods in comparison to existing fast monocular depth estimation methodologies on the KITTI dataset.
Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the complex pose and shape parameters from coupled image features, whose high complexity and low representation ability often result in inconsistent pose motion and limited shape patterns. To alleviate this issue, we introduce 3D pose as the intermediary and propose a Pose and Mesh Co-Evolution network (PMCE) that decouples this task into two parts: 1) video-based 3D human pose estimation and 2) mesh vertices regression from the estimated 3D pose and temporal image feature. Specifically, we propose a two-stream encoder that estimates mid-frame 3D pose and extracts a temporal image feature from the input image sequence. In addition, we design a co-evolution decoder that performs pose and mesh interactions with the image-guided Adaptive Layer Normalization (AdaLN) to make pose and mesh fit the human body shape. Extensive experiments demonstrate that the proposed PMCE outperforms previous state-of-the-art methods in terms of both per-frame accuracy and temporal consistency on three benchmark datasets: 3DPW, Human3.6M, and MPI-INF-3DHP. Our code is available at https://github.com/kasvii/PMCE.
Existing techniques for text detection can be broadly classified into two primary groups: segmentation-based and regression-based methods. Segmentation models offer enhanced robustness to font variations but require intricate post-processing, leading to high computational overhead. Regression-based methods undertake instance-aware prediction but face limitations in robustness and data efficiency due to their reliance on high-level representations. In our academic pursuit, we propose SRFormer, a unified DETR-based model with amalgamated Segmentation and Regression, aiming at the synergistic harnessing of the inherent robustness in segmentation representations, along with the straightforward post-processing of instance-level regression. Our empirical analysis indicates that favorable segmentation predictions can be obtained at the initial decoder layers. In light of this, we constrain the incorporation of segmentation branches to the first few decoder layers and employ progressive regression refinement in subsequent layers, achieving performance gains while minimizing computational load from the mask.Furthermore, we propose a Mask-informed Query Enhancement module. We take the segmentation result as a natural soft-ROI to pool and extract robust pixel representations, which are then employed to enhance and diversify instance queries. Extensive experimentation across multiple benchmarks has yielded compelling findings, highlighting our method's exceptional robustness, superior training and data efficiency, as well as its state-of-the-art performance. Our code is available at https://github.com/retsuh-bqw/SRFormer-Text-Det.
Phase information has a significant impact on speech perceptual quality and intelligibility. However, existing speech enhancement methods encounter limitations in explicit phase estimation due to the non-structural nature and wrapping characteristics of the phase, leading to a bottleneck in enhanced speech quality. To overcome the above issue, in this paper, we proposed MP-SENet, a novel Speech Enhancement Network that explicitly enhances Magnitude and Phase spectra in parallel. The proposed MP-SENet comprises a Transformer-embedded encoder-decoder architecture. The encoder aims to encode the input distorted magnitude and phase spectra into time-frequency representations, which are further fed into time-frequency Transformers for alternatively capturing time and frequency dependencies. The decoder comprises a magnitude mask decoder and a phase decoder, directly enhancing magnitude and wrapped phase spectra by incorporating a magnitude masking architecture and a phase parallel estimation architecture, respectively. Multi-level loss functions explicitly defined on the magnitude spectra, wrapped phase spectra, and short-time complex spectra are adopted to jointly train the MP-SENet model. A metric discriminator is further employed to compensate for the incomplete correlation between these losses and human auditory perception. Experimental results demonstrate that our proposed MP-SENet achieves state-of-the-art performance across multiple speech enhancement tasks, including speech denoising, dereverberation, and bandwidth extension. Compared to existing phase-aware speech enhancement methods, it further mitigates the compensation effect between the magnitude and phase by explicit phase estimation, elevating the perceptual quality of enhanced speech.
Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satisfactory performance in downstream tasks. As large language models (LLMs) have demonstrated remarkable performance, it is intriguing to investigate whether CF exists during the continual instruction tuning of LLMs. This study empirically evaluates the forgetting phenomenon in LLMs' knowledge during continual instruction tuning from the perspectives of domain knowledge, reasoning, and reading comprehension. The experiments reveal that catastrophic forgetting is generally observed in LLMs ranging from 1b to 7b parameters. Surprisingly, as the model scale increases, the severity of forgetting intensifies in such a model sale range which may result from the much significant initial performance in the larger LLM. Comparing the decoder-only model BLOOMZ with the encoder-decoder model mT0, BLOOMZ exhibits less forgetting and retains more knowledge. Interestingly, we also observe that LLMs can mitigate language biases, such as gender bias, during continual fine-tuning. Furthermore, our findings indicate that general instruction tuning can help alleviate the forgetting phenomenon in LLMs during subsequent fine-tuning.
Language models are useful adjuncts to optical models for producing accurate optical character recognition (OCR) results. One factor which limits the power of language models in this context is the existence of many specialized domains with language statistics very different from those implied by a general language model - think of checks, medical prescriptions, and many other specialized document classes. This paper introduces an algorithm for efficiently generating and attaching a domain specific word based language model at run time to a general language model in an OCR system. In order to best use this model the paper also introduces a modified CTC beam search decoder which effectively allows hypotheses to remain in contention based on possible future completion of vocabulary words. The result is a substantial reduction in word error rate in recognizing material from specialized domains.
Deep neural operators (DNOs) have been utilized to approximate nonlinear mappings between function spaces. However, DNOs face the challenge of increased dimensionality and computational cost associated with unaligned observation data. In this study, we propose a hybrid Decoder-DeepONet operator regression framework to handle unaligned data effectively. Additionally, we introduce a Multi-Decoder-DeepONet, which utilizes an average field of training data as input augmentation. The consistencies of the frameworks with the operator approximation theory are provided, on the basis of the universal approximation theorem. Two numerical experiments, Darcy problem and flow-field around an airfoil, are conducted to validate the efficiency and accuracy of the proposed methods. Results illustrate the advantages of Decoder-DeepONet and Multi-Decoder-DeepONet in handling unaligned observation data and showcase their potentials in improving prediction accuracy.