NExT-Chat: An LMM for Chat, Detection and Segmentation

Ao Zhang, Yuan Yao, Wei Ji, Zhiyuan Liu, Tat-Seng Chua
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60116-60133, 2024.

Abstract

The development of large language models (LLMs) has greatly advanced the field of multimodal understanding, leading to the emergence of large multimodal models (LMMs). In order to enhance visual comprehension, recent studies have equipped LMMs with region-level understanding capabilities by representing object bounding box coordinates as a series of text sequences (pix2seq). In this paper, we introduce a novel paradigm for object location modeling called the pix2emb method, where we ask the LMM to output the location embeddings and then decode them with different decoders. This paradigm allows us to use different location formats (such as bounding boxes and masks) in multimodal conversations. Leveraging the proposed pix2emb method, we train an LMM named NExT-Chat and demonstrate its capability of handling multiple tasks like visual grounding, region captioning, and grounded reasoning. Comprehensive experiments show the effectiveness of our NExT-Chat on various tasks, e.g., NExT-Chat (87.7) vs. Shikra (86.9) on POPE-Random, NExT-Chat (71.3) vs. LISA (67.9) on referring expression segmentation task, and NExT-Chat (79.6) vs. Kosmos-2 (62.3) on region caption task.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-zhang24bu, title = {{NE}x{T}-Chat: An {LMM} for Chat, Detection and Segmentation}, author = {Zhang, Ao and Yao, Yuan and Ji, Wei and Liu, Zhiyuan and Chua, Tat-Seng}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {60116--60133}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/zhang24bu/zhang24bu.pdf}, url = {https://proceedings.mlr.press/v235/zhang24bu.html}, abstract = {The development of large language models (LLMs) has greatly advanced the field of multimodal understanding, leading to the emergence of large multimodal models (LMMs). In order to enhance visual comprehension, recent studies have equipped LMMs with region-level understanding capabilities by representing object bounding box coordinates as a series of text sequences (pix2seq). In this paper, we introduce a novel paradigm for object location modeling called the pix2emb method, where we ask the LMM to output the location embeddings and then decode them with different decoders. This paradigm allows us to use different location formats (such as bounding boxes and masks) in multimodal conversations. Leveraging the proposed pix2emb method, we train an LMM named NExT-Chat and demonstrate its capability of handling multiple tasks like visual grounding, region captioning, and grounded reasoning. Comprehensive experiments show the effectiveness of our NExT-Chat on various tasks, e.g., NExT-Chat (87.7) vs. Shikra (86.9) on POPE-Random, NExT-Chat (71.3) vs. LISA (67.9) on referring expression segmentation task, and NExT-Chat (79.6) vs. Kosmos-2 (62.3) on region caption task.} }
Endnote
%0 Conference Paper %T NExT-Chat: An LMM for Chat, Detection and Segmentation %A Ao Zhang %A Yuan Yao %A Wei Ji %A Zhiyuan Liu %A Tat-Seng Chua %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-zhang24bu %I PMLR %P 60116--60133 %U https://proceedings.mlr.press/v235/zhang24bu.html %V 235 %X The development of large language models (LLMs) has greatly advanced the field of multimodal understanding, leading to the emergence of large multimodal models (LMMs). In order to enhance visual comprehension, recent studies have equipped LMMs with region-level understanding capabilities by representing object bounding box coordinates as a series of text sequences (pix2seq). In this paper, we introduce a novel paradigm for object location modeling called the pix2emb method, where we ask the LMM to output the location embeddings and then decode them with different decoders. This paradigm allows us to use different location formats (such as bounding boxes and masks) in multimodal conversations. Leveraging the proposed pix2emb method, we train an LMM named NExT-Chat and demonstrate its capability of handling multiple tasks like visual grounding, region captioning, and grounded reasoning. Comprehensive experiments show the effectiveness of our NExT-Chat on various tasks, e.g., NExT-Chat (87.7) vs. Shikra (86.9) on POPE-Random, NExT-Chat (71.3) vs. LISA (67.9) on referring expression segmentation task, and NExT-Chat (79.6) vs. Kosmos-2 (62.3) on region caption task.
APA
Zhang, A., Yao, Y., Ji, W., Liu, Z. & Chua, T.. (2024). NExT-Chat: An LMM for Chat, Detection and Segmentation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:60116-60133 Available from https://proceedings.mlr.press/v235/zhang24bu.html.

Related Material