Meta recently released SAM (Segment Anything Model) which is a general-purpose segmentation model. SAM has shown promising results in a wide variety of segmentation tasks including medical image segmentation. In the field of medical image segmentation, polyp segmentation holds a position of high importance, thus creating a model which is robust and precise is quite challenging. Polyp segmentation is a fundamental task to ensure better diagnosis and cure of colorectal cancer. As such in this study, we will see how Polyp-SAM++, a text prompt-aided SAM, can better utilize a SAM using text prompting for robust and more precise polyp segmentation. We will evaluate the performance of a text-guided SAM on the polyp segmentation task on benchmark datasets. We will also compare the results of text-guided SAM vs unprompted SAM. With this study, we hope to advance the field of polyp segmentation and inspire more, intriguing research. The code and other details will be made publically available soon at https://github.com/RisabBiswas/Polyp-SAM++.
Knowledge-based Visual Question Answering (KB-VQA) requires VQA systems to utilize knowledge from existing knowledge bases to answer visually-grounded questions. Retrieval-Augmented Visual Question Answering (RA-VQA), a strong framework to tackle KB-VQA, first retrieves related documents with Dense Passage Retrieval (DPR) and then uses them to answer questions. This paper proposes Fine-grained Late-interaction Multi-modal Retrieval (FLMR) which significantly improves knowledge retrieval in RA-VQA. FLMR addresses two major limitations in RA-VQA's retriever: (1) the image representations obtained via image-to-text transforms can be incomplete and inaccurate and (2) relevance scores between queries and documents are computed with one-dimensional embeddings, which can be insensitive to finer-grained relevance. FLMR overcomes these limitations by obtaining image representations that complement those from the image-to-text transforms using a vision model aligned with an existing text-based retriever through a simple alignment network. FLMR also encodes images and questions using multi-dimensional embeddings to capture finer-grained relevance between queries and documents. FLMR significantly improves the original RA-VQA retriever's PRRecall@5 by approximately 8\%. Finally, we equipped RA-VQA with two state-of-the-art large multi-modal/language models to achieve $\sim61\%$ VQA score in the OK-VQA dataset.
Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through additional visual guidance (e.g, sketches and semantic masks) but require additional training with annotated images. In this paper, we propose a method for spatially controlling text-to-image generation without further training of diffusion models. Our method is based on the insight that the cross-attention maps reflect the positional relationship between words and pixels. Our aim is to control the attention maps according to given semantic masks and text prompts. To this end, we first explore a simple approach of directly swapping the cross-attention maps with constant maps computed from the semantic regions. Moreover, we propose masked-attention guidance, which can generate images more faithful to semantic masks than the first approach. Masked-attention guidance indirectly controls attention to each word and pixel according to the semantic regions by manipulating noise images fed to diffusion models. Experiments show that our method enables more accurate spatial control than baselines qualitatively and quantitatively.
Despite recent research advancements in reconstructing clothed humans from a single image, accurately restoring the "unseen regions" with high-level details remains an unsolved challenge that lacks attention. Existing methods often generate overly smooth back-side surfaces with a blurry texture. But how to effectively capture all visual attributes of an individual from a single image, which are sufficient to reconstruct unseen areas (e.g., the back view)? Motivated by the power of foundation models, TeCH reconstructs the 3D human by leveraging 1) descriptive text prompts (e.g., garments, colors, hairstyles) which are automatically generated via a garment parsing model and Visual Question Answering (VQA), 2) a personalized fine-tuned Text-to-Image diffusion model (T2I) which learns the "indescribable" appearance. To represent high-resolution 3D clothed humans at an affordable cost, we propose a hybrid 3D representation based on DMTet, which consists of an explicit body shape grid and an implicit distance field. Guided by the descriptive prompts + personalized T2I diffusion model, the geometry and texture of the 3D humans are optimized through multi-view Score Distillation Sampling (SDS) and reconstruction losses based on the original observation. TeCH produces high-fidelity 3D clothed humans with consistent & delicate texture, and detailed full-body geometry. Quantitative and qualitative experiments demonstrate that TeCH outperforms the state-of-the-art methods in terms of reconstruction accuracy and rendering quality. The code will be publicly available for research purposes at https://huangyangyi.github.io/TeCH
Depression is a mental health disorder that has a profound impact on people's lives. Recent research suggests that signs of depression can be detected in the way individuals communicate, both through spoken words and written texts. In particular, social media posts are a rich and convenient text source that we may examine for depressive symptoms. The Beck Depression Inventory (BDI) Questionnaire, which is frequently used to gauge the severity of depression, is one instrument that can aid in this study. We can narrow our study to only those symptoms since each BDI question is linked to a particular depressive symptom. It's important to remember that not everyone with depression exhibits all symptoms at once, but rather a combination of them. Therefore, it is extremely useful to be able to determine if a sentence or a piece of user-generated content is pertinent to a certain condition. With this in mind, the eRisk 2023 Task 1 was designed to do exactly that: assess the relevance of different sentences to the symptoms of depression as outlined in the BDI questionnaire. This report is all about how our team, Mason-NLP, participated in this subtask, which involved identifying sentences related to different depression symptoms. We used a deep learning approach that incorporated MentalBERT, RoBERTa, and LSTM. Despite our efforts, the evaluation results were lower than expected, underscoring the challenges inherent in ranking sentences from an extensive dataset about depression, which necessitates both appropriate methodological choices and significant computational resources. We anticipate that future iterations of this shared task will yield improved results as our understanding and techniques evolve.
This paper explores predicting suitable prosodic features for fine-grained emotion analysis from the discourse-level text. To obtain fine-grained emotional prosodic features as predictive values for our model, we extract a phoneme-level Local Prosody Embedding sequence (LPEs) and a Global Style Embedding as prosodic speech features from the speech with the help of a style transfer model. We propose a Discourse-level Multi-scale text Prosodic Model (D-MPM) that exploits multi-scale text to predict these two prosodic features. The proposed model can be used to analyze better emotional prosodic features and thus guide the speech synthesis model to synthesize more expressive speech. To quantitatively evaluate the proposed model, we contribute a new and large-scale Discourse-level Chinese Audiobook (DCA) dataset with more than 13,000 utterances annotated sequences to evaluate the proposed model. Experimental results on the DCA dataset show that the multi-scale text information effectively helps to predict prosodic features, and the discourse-level text improves both the overall coherence and the user experience. More interestingly, although we aim at the synthesis effect of the style transfer model, the synthesized speech by the proposed text prosodic analysis model is even better than the style transfer from the original speech in some user evaluation indicators.
As the size of Large Multi-Modal Models (LMMs) increases consistently, the adaptation of these pre-trained models to specialized tasks has become a computationally and memory-intensive challenge. Traditional fine-tuning methods require isolated, exhaustive retuning for each new task, limiting the models' versatility. Moreover, current efficient adaptation techniques often overlook modality alignment, focusing only on the knowledge extraction of new tasks. To tackle these issues, we introduce Multiway-Adapter, an innovative framework incorporating an 'Alignment Enhancer' to deepen modality alignment, enabling high transferability without tuning pre-trained parameters. Our method adds fewer than 1.25\% of additional parameters to LMMs, exemplified by the BEiT-3 model in our study. This leads to superior zero-shot image-text retrieval performance compared to fully fine-tuned models, while achieving up to a 57\% reduction in fine-tuning time. Our approach offers a resource-efficient and effective adaptation pathway for LMMs, broadening their applicability. The source code is publicly available at: \url{https://github.com/longkukuhi/MultiWay-Adapter}.
In recent years, advances in the large-scale pretraining of language and text-to-image models have revolutionized the field of machine learning. Yet, integrating these two modalities into a single, robust model capable of generating seamless multimodal outputs remains a significant challenge. To address this gap, we present the Joint Autoregressive Mixture (JAM) framework, a modular approach that systematically fuses existing text and image generation models. We also introduce a specialized, data-efficient instruction-tuning strategy, tailored for mixed-modal generation tasks. Our final instruct-tuned model demonstrates unparalleled performance in generating high-quality multimodal outputs and represents the first model explicitly designed for this purpose.
Recent advances in text-to-image diffusion models have enabled 3D generation from a single image. However, current image-to-3D methods often produce suboptimal results for novel views, with blurred textures and deviations from the reference image, limiting their practical applications. In this paper, we introduce HiFi-123, a method designed for high-fidelity and multi-view consistent 3D generation. Our contributions are twofold: First, we propose a reference-guided novel view enhancement technique that substantially reduces the quality gap between synthesized and reference views. Second, capitalizing on the novel view enhancement, we present a novel reference-guided state distillation loss. When incorporated into the optimization-based image-to-3D pipeline, our method significantly improves 3D generation quality, achieving state-of-the-art performance. Comprehensive evaluations demonstrate the effectiveness of our approach over existing methods, both qualitatively and quantitatively.
We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate speech transcription contexts. This marks a step towards a fresh paradigm in generative error correction within the realm of n-best hypotheses. Unlike the existing ranking-based rescoring methods, our approach adeptly uses distinct initialization techniques and parameter-efficient algorithms to boost ASR performance derived from pre-trained speech and text models. Through evaluation across diverse ASR datasets, we evaluate the stability and reproducibility of our fusion technique, demonstrating its improved word error rate relative (WERR) performance in comparison to n-best hypotheses by relatively 37.66%. To encourage future research, we have made our code and pre-trained models open source at https://github.com/Srijith-rkr/Whispering-LLaMA.